Huggingface transformer does not load as expected

Nobody has claimed this yet.

Hello,

Instead of using `sentence-transformers/all-MiniLM-L6-v2`, I wanted to try out a custom embedding model from Huggingface. I read previous opened and closed issues and found the following approaches:


Code:

```python
# romanian_embedding_model = pipeline("feature-extraction", model="readerbench/RoBERT-large", tokenizer="readerbench/RoBERT-large")
# tokenizer_kwargs = {'padding':True,'truncation':True,'max_length':512,'return_tensors':'pt'}
# self.bertopic_model = BERTopic(embedding_model=lambda x: romanian_embedding_model(x, **tokenizer_kwargs), verbose=True, nr_topics='auto', n_gram_range=(1, 2))
# topics_1, probs_1 = self.bertopic_model.fit_transform(self.nontruncated_documents)
embedding_model = AutoModel.from_pretrained("dumitrescustefan/bert-base-romanian-cased-v1")
tokenizer = AutoTokenizer.from_pretrained("dumitrescustefan/bert-base-romanian-cased-v1")
romanian_embedding_model = pipeline("feature-extraction", model=embedding_model, tokenizer=tokenizer)
tokenizer_kwargs = {'padding':True, 'truncation':True, 'max_length':512, 'return_tensors':'pt'}
self.bertopic_model = BERTopic(embedding_model=lambda x: romanian_embedding_model(x, **tokenizer_kwargs), verbose=True, nr_topics='auto', n_gram_range=(1, 2))
topics_1, probs_1 = self.bertopic_model.fit_transform(self.nontruncated_documents)
```

However, by using a logger like

```python
import logging
logging.basicConfig()
logger = logging.getLogger('Something')
logger.setLevel(logging.INFO)
```

... I discovered that BERTopic doesn't actually load the Huggingface model. It simply loads `sentence-transformers/all-MiniLM-L6-v2`. Why is this the case?

Proof:


I will use the multilingual version until this issue is fixed.

Thank you for your patience 💯

Start by reproducing the shown BERTopic setup with the Hugging Face pipeline, AutoModel, and AutoTokenizer while observing the logger output. Trace how BERTopic handles the callable passed as embedding_model and determine whether the custom Romanian model is actually selected; done means the supplied model is used instead of sentence-transformers/all-MiniLM-L6-v2.

Written by the indexing model from the issue text.